© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48730
    Prev
    Next
    INDEX
    Explanations

    scope

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tritur
    -0.09
     tritur
    -0.08
     achterkant
    -0.08
     thawj
    -0.08
     estamp
    -0.08
     feem
    -0.08
     přev
    -0.08
     qauv
    -0.08
    娱乐平台
    -0.07
     đông
    -0.07
    POSITIVE LOGITS
     scope
    0.34
     Scope
    0.32
     scopes
    0.31
    Scope
    0.31
    _scope
    0.31
    scope
    0.31
    	scope
    0.30
    .scope
    0.30
     scoped
    0.28
    (scope
    0.28
    Activations Density 0.059%

    No Known Activations