Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1601
    Prev
    Next
    INDEX
    Explanations

    sky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acum
    -0.08
     Georgetown
    -0.08
    .Ob
    -0.08
    ecan
    -0.07
    Dette
    -0.07
     Cumhur
    -0.07
     ron
    -0.07
    മാണ
    -0.07
     Télé
    -0.07
     Baş
    -0.07
    POSITIVE LOGITS
    �
    0.08
    �
    0.08
    лау
    0.08
    ောင်း
    0.08
    _story
    0.08
    auk
    0.08
    abile
    0.07
    ged
    0.07
     bx
    0.07
    нят
    0.07
    Activations Density 0.020%

    No Known Activations