© 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. 97374
    Prev
    Next
    INDEX
    Explanations

    .get

    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
     External
    -0.09
    _external
    -0.09
    _values
    -0.09
    _child
    -0.09
    _messages
    -0.09
    _from
    -0.09
    _array
    -0.09
    _image
    -0.09
    External
    -0.09
    _class
    -0.09
    POSITIVE LOGITS
    “一
    0.08
    pee
    0.08
    (identity
    0.08
    identity
    0.08
    pause
    0.08
    ','#
    0.08
    MHz
    0.07
    doğan
    0.07
    ('{}
    0.07
     repeal
    0.07
    Activations Density 0.001%

    No Known Activations