© 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. 19-RESID-POST-AA
    11. 102666
    Prev
    Next
    INDEX
    Explanations

    = /

    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
    's
    -0.08
     both
    -0.08
    'label
    -0.07
    All
    -0.07
    _ALL
    -0.07
     Both
    -0.07
    ਨਾ
    -0.07
    `s
    -0.07
    Both
    -0.07
     Städ
    -0.07
    POSITIVE LOGITS
    րաստ
    0.10
    եխն
    0.10
    րանս
    0.09
    արաբաղ
    0.09
    ამაშ
    0.09
    ��
    0.09
     ყოველ
    0.09
    imuhamed
    0.09
    ապարհ
    0.09
     伟德
    0.09
    Activations Density 0.016%

    No Known Activations