© 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. 11-RESID-POST-AA
    11. 95416
    Prev
    Next
    INDEX
    Explanations

    3

    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
     ರಾಷ್ಟ
    -0.08
     ದೇಶ
    -0.08
    インチ
    -0.08
    countries
    -0.08
     جمه
    -0.08
     frying
    -0.07
     fabricación
    -0.07
     देश
    -0.07
     fabricação
    -0.07
    .country
    -0.07
    POSITIVE LOGITS
     borderline
    0.13
     Grenze
    0.10
     boundary
    0.09
    boundary
    0.09
    _boundary
    0.09
    =edge
    0.08
    exact
    0.08
    -edge
    0.08
     barely
    0.08
     Boundary
    0.08
    Activations Density 0.079%

    No Known Activations