© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 52005
    Prev
    Next
    INDEX
    Explanations

    lang

    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
    வு
    -0.09
    barkeit
    -0.09
    ిగ
    -0.08
     gata
    -0.08
    itated
    -0.08
    ుగ
    -0.08
    ిగి
    -0.08
    legen
    -0.08
    legte
    -0.08
    ნა
    -0.07
    POSITIVE LOGITS
    ıç
    0.12
    ì
    0.09
    Nonce
    0.09
    Count
    0.08
    âng
    0.08
    ang
    0.08
    (at
    0.08
    ABCDE
    0.08
     counting
    0.08
    -count
    0.08
    Activations Density 0.000%

    No Known Activations