© 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. 30163
    Prev
    Next
    INDEX
    Explanations

    Hindi

    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
     floated
    -0.08
    ене
    -0.07
    cheduled
    -0.07
    Finger
    -0.07
     flotation
    -0.07
     endorsed
    -0.07
    ंख
    -0.07
    吊
    -0.07
     diagnostics
    -0.07
    унок
    -0.07
    POSITIVE LOGITS
    -speaking
    0.12
    -English
    0.08
     speakers
    0.08
     collectiv
    0.08
    531
    0.08
     మాట్లాడ
    0.08
     plains
    0.07
     تعالى
    0.07
     ಮಾತನಾಡ
    0.07
    യിൽ
    0.07
    Activations Density 0.005%

    No Known Activations