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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1561
    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_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vow
    -0.09
    _FATAL
    -0.08
    Requirement
    -0.08
    enschaft
    -0.08
     Words
    -0.07
    665
    -0.07
    ₂
    -0.07
    skraft
    -0.07
     opges
    -0.07
    _MULTI
    -0.07
    POSITIVE LOGITS
     나타
    0.08
     occupants
    0.08
     پرس
    0.08
     स्वागत
    0.08
     taxis
    0.08
     flora
    0.07
    ctions
    0.07
     안내
    0.07
     ters
    0.07
     inhabitants
    0.07
    Activations Density 0.075%

    No Known Activations