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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55906
    Prev
    Next
    INDEX
    Explanations

    equilateral triangle centers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SORT
    -0.09
    Verb
    -0.08
    Realtime
    -0.08
    Archived
    -0.08
     Boca
    -0.08
    .verify
    -0.07
    _SCREEN
    -0.07
    VIEW
    -0.07
    FIT
    -0.07
     업데이트
    -0.07
    POSITIVE LOGITS
     centroid
    0.09
     coincide
    0.09
     مرکز
    0.08
     ಕೇಂದ್ರ
    0.08
    ancel
    0.08
     layers
    0.08
     ચાલી
    0.08
    occus
    0.08
     devido
    0.08
    ophy
    0.08
    Activations Density 0.014%

    No Known Activations