© 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. 65020
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     घे
    -0.09
    /DD
    -0.08
    /photo
    -0.08
     घेत
    -0.07
     जमा
    -0.07
     తీస
    -0.07
     photo
    -0.07
     elsker
    -0.07
    _FL
    -0.07
     मुक
    -0.07
    POSITIVE LOGITS
    xiom
    0.10
     dictum
    0.10
     RULE
    0.09
    phr
    0.09
     Conversely
    0.09
    句
    0.09
    句话
    0.08
     vận
    0.08
    RULE
    0.08
     משפט
    0.08
    Activations Density 0.046%

    No Known Activations