© 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. 26471
    Prev
    Next
    INDEX
    Explanations

    foreign languages and position

    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
     escorted
    -0.10
    Investig
    -0.08
     Chr
    -0.08
    umerator
    -0.08
    Sesion
    -0.08
    орус
    -0.08
    Paid
    -0.08
    ographers
    -0.08
    ensp
    -0.08
    ographer
    -0.07
    POSITIVE LOGITS
     ability
    0.20
     সক্ষম
    0.18
     capability
    0.18
     Ability
    0.17
     abilities
    0.16
     Fähigkeit
    0.16
     capabilities
    0.16
    Ability
    0.16
    能力
    0.16
     Capability
    0.15
    Activations Density 0.042%

    No Known Activations