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. 43701
    Prev
    Next
    INDEX
    Explanations

    im

    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
    261
    -0.09
    Recovered
    -0.07
    .Users
    -0.07
    _chip
    -0.07
     driven
    -0.07
    ಾಗಿದೆ
    -0.07
     EZ
    -0.07
    .-
    -0.07
    Chip
    -0.07
    Usu
    -0.07
    POSITIVE LOGITS
    (INVOK
    0.09
    _keywords
    0.08
     minst
    0.08
     Include
    0.08
    otipo
    0.08
    _expr
    0.07
     sudah
    0.07
    gender
    0.07
    "strconv
    0.07
     Нар
    0.07
    Activations Density 0.012%

    No Known Activations