© 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. 65362
    Prev
    Next
    INDEX
    Explanations

    geometric inequalities

    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
     bilingual
    -0.08
     plaid
    -0.07
     Franken
    -0.07
     retention
    -0.07
     graffiti
    -0.07
     somit
    -0.07
     unterstützen
    -0.07
     Sext
    -0.07
     mehrere
    -0.07
     teal
    -0.07
    POSITIVE LOGITS
     योग
    0.09
     Leia
    0.09
    غه
    0.09
     carn
    0.09
     katerih
    0.09
     pake
    0.08
     forb
    0.08
     आवश्यकता
    0.08
     जर
    0.08
     violate
    0.08
    Activations Density 0.022%

    No Known Activations