© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 18781
    Prev
    Next
    INDEX
    Explanations

    Importance or emphasis on

    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
     سوم
    -0.09
    <|reserved_200000|>
    -0.09
    ្មី
    -0.09
     kuphela
    -0.09
    ույց
    -0.09
     prostu
    -0.09
    <|endofprompt|>
    -0.09
     ',
    -0.09
     сондай
    -0.09
     թվական
    -0.09
    POSITIVE LOGITS
     of
    0.13
    .
    0.11
     to
    0.10
    ในการ
    0.09
     של
    0.09
     for
    0.09
    .↵↵
    0.08
     in
    0.08
     regarding
    0.08
    e
    0.08
    Activations Density 0.577%

    No Known Activations