© 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. 11-RESID-POST-AA
    11. 70329
    Prev
    Next
    INDEX
    Explanations

    adjacency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     active
    -0.09
     activa
    -0.09
     secundaria
    -0.08
    active
    -0.08
    _active
    -0.08
    Active
    -0.08
    _ACTIVE
    -0.08
     সাম
    -0.08
     ACTIVE
    -0.07
     esf
    -0.07
    POSITIVE LOGITS
    _sid
    0.08
    Sid
    0.08
     adel
    0.08
    878
    0.07
    己
    0.07
    557
    0.07
     dred
    0.07
     Modules
    0.07
     opat
    0.07
    574
    0.07
    Activations Density 0.013%

    No Known Activations