© 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. 29642
    Prev
    Next
    INDEX
    Explanations

    research scope

    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
     plating
    -0.08
     platos
    -0.08
     plated
    -0.07
     plato
    -0.07
    bour
    -0.07
     поль
    -0.07
     GOLD
    -0.07
     apel
    -0.07
     largos
    -0.07
     alum
    -0.07
    POSITIVE LOGITS
     Scope
    0.19
     scope
    0.17
    Scope
    0.17
    _scope
    0.16
    scope
    0.16
    .scope
    0.15
    _SCOPE
    0.15
    (scope
    0.15
    	scope
    0.14
    范围
    0.14
    Activations Density 0.030%

    No Known Activations