© 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. 102712
    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
     new
    -0.08
    son
    -0.08
    case
    -0.08
    ong
    -0.08
     lame
    -0.08
    htub
    -0.07
    SON
    -0.07
    ws
    -0.07
     old
    -0.07
     more
    -0.07
    POSITIVE LOGITS
     Ị
    0.09
     ('$
    0.09
    (minutes
    0.09
    ნით
    0.09
    …I
    0.09
    ,'%
    0.08
    ‘I
    0.08
     iyadoo
    0.08
    ümay
    0.08
    -ready
    0.08
    Activations Density 0.001%

    No Known Activations