© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19018
    Prev
    Next
    INDEX
    Explanations

    positions/groupings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expressly
    -0.10
     específicos
    -0.08
    طن
    -0.08
    .loss
    -0.08
     überall
    -0.08
    Others
    -0.08
     won't
    -0.08
     dafür
    -0.08
     diversos
    -0.08
    ضمن
    -0.08
    POSITIVE LOGITS
     positions
    0.15
     indices
    0.14
     vertices
    0.12
     pairs
    0.12
     index
    0.12
    positions
    0.12
     possible
    0.11
    _positions
    0.11
     Positions
    0.11
     indexing
    0.11
    Activations Density 0.028%

    No Known Activations