© 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. 54877
    Prev
    Next
    INDEX
    Explanations

    mixed languages/translations

    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
    TOT
    -0.09
    Tot
    -0.08
    외
    -0.07
    Rah
    -0.07
    rip
    -0.07
     Leop
    -0.07
    segunda
    -0.07
    Zap
    -0.07
    Hop
    -0.07
     Rah
    -0.07
    POSITIVE LOGITS
     मात्रा
    0.12
    Amounts
    0.10
     amounts
    0.10
     portion
    0.10
     количества
    0.10
    _amount
    0.10
    _AMOUNT
    0.10
     cantidades
    0.10
     रकम
    0.10
     количество
    0.09
    Activations Density 0.069%

    No Known Activations