© 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. 23-RESID-POST-AA
    11. 51711
    Prev
    Next
    INDEX
    Explanations

    Dan

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concentrated
    -0.08
     maintained
    -0.08
     Heavy
    -0.08
     mass
    -0.08
    ipto
    -0.07
     heavier
    -0.07
    Mass
    -0.07
    itus
    -0.07
    acial
    -0.07
     Mass
    -0.07
    POSITIVE LOGITS
    ube
    0.10
    çando
    0.10
    UBE
    0.09
    ĝ
    0.08
    /ne
    0.08
    ub
    0.08
    เจ
    0.07
     แจ
    0.07
     objectif
    0.07
     sperm
    0.07
    Activations Density 0.002%

    No Known Activations