© 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. 102634
    Prev
    Next
    INDEX
    Explanations

    Math computations

    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
    achable
    -0.08
    plex
    -0.08
     Antiqu
    -0.07
    ાસ્ત
    -0.07
     planets
    -0.07
     sets
    -0.07
    יתוח
    -0.07
    ants
    -0.07
     Mountains
    -0.07
     bunch
    -0.07
    POSITIVE LOGITS
    UILabel
    0.09
     പുറ
    0.09
     rağ
    0.09
     kendi
    0.09
    $field
    0.09
     kullanıcı
    0.08
     innlegg
    0.08
    'label
    0.08
     zvakare
    0.08
     bedienen
    0.08
    Activations Density 0.010%

    No Known Activations