© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48455
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    ています
    -0.32
    た
    -0.28
    ಿದೆ
    -0.26
    ுகிறது
    -0.22
    たり
    -0.22
    ા
    -0.14
    ных
    -0.13
    ный
    -0.12
    ൻ
    -0.12
    ного
    -0.12
    POSITIVE LOGITS
     бұрын
    0.08
    었던
    0.08
     LAW
    0.08
    ုပ
    0.07
    ပ်
    0.07
    woordig
    0.07
    iul
    0.07
    гүй
    0.07
    cies
    0.07
    ктің
    0.07
    Activations Density 0.084%

    No Known Activations