© 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. 18695
    Prev
    Next
    INDEX
    Explanations

    say punctuation

    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
    -0.10
    rọ
    -0.09
    uanya
    -0.09
    daky
    -0.09
    anjeunna
    -0.09
    ಬೆಂಗಳೂರು
    -0.08
    ტაბ
    -0.08
     soň
    -0.08
    Then
    -0.08
     taýdan
    -0.08
    POSITIVE LOGITS
    <|reserved_200004|>
    0.17
    ,
    0.15
    ،
    0.14
    ),
    0.14
    )
    0.13
    ):↵
    0.13
    ).
    0.12
    ,”
    0.12
    .
    0.12
    )의
    0.11
    Activations Density 0.155%

    No Known Activations