© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94950
    Prev
    Next
    INDEX
    Explanations

    downward-opening parabolas

    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
    .repository
    -0.10
    .kafka
    -0.09
     loaders
    -0.09
    .loader
    -0.09
     Repository
    -0.09
    ollower
    -0.09
    (loader
    -0.08
     kos
    -0.08
     unsettling
    -0.08
    loader
    -0.08
    POSITIVE LOGITS
     maxim
    0.16
     maximize
    0.15
     maximizing
    0.14
     Maxim
    0.13
     Максим
    0.12
     máxim
    0.12
    最大
    0.12
    maximize
    0.11
     maxima
    0.11
     maximise
    0.11
    Activations Density 0.071%

    No Known Activations