© 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. 3-RESID-POST-AA
    11. 1348
    Prev
    Next
    INDEX
    Explanations

    text sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     walkway
    -0.08
     Cas
    -0.07
     Î
    -0.07
     IFC
    -0.07
     транспорт
    -0.07
     Onder
    -0.07
     Stevie
    -0.07
    836
    -0.07
     oni
    -0.07
     yourselves
    -0.07
    POSITIVE LOGITS
     emph
    0.08
    Rid
    0.08
    _tid
    0.08
    ítico
    0.08
    这里只
    0.08
    苦
    0.08
    ẹp
    0.07
    �
    0.07
    	Vector
    0.07
     sple
    0.07
    Activations Density 0.155%

    No Known Activations