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. 77229
    Prev
    Next
    INDEX
    Explanations

    3DMark benchmarks

    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
     decidedly
    -0.10
    Excluded
    -0.08
    gas
    -0.08
     downfall
    -0.08
    decision
    -0.08
    -Cs
    -0.08
     రాజకీయ
    -0.07
     gastrointestinal
    -0.07
     aquella
    -0.07
     بالر
    -0.07
    POSITIVE LOGITS
     нормы
    0.08
     library
    0.07
     normals
    0.07
     residual
    0.07
    (norm
    0.07
     lateral
    0.07
     Moll
    0.07
     Norman
    0.07
     rang
    0.07
     sala
    0.07
    Activations Density 0.001%

    No Known Activations