Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112811
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    _native
    -0.08
     Holy
    -0.07
    agun
    -0.07
     Apar
    -0.07
     Fixed
    -0.07
     references
    -0.07
     Hermione
    -0.07
    Fixed
    -0.07
     Custom
    -0.07
     Decimal
    -0.07
    POSITIVE LOGITS
     अच्छा
    0.10
     интересно
    0.09
     spannend
    0.09
     нравится
    0.08
    ดี
    0.08
     буде
    0.08
    加坡
    0.08
     cukup
    0.08
     قلي
    0.08
     좋
    0.08
    Activations Density 0.016%

    No Known Activations