© 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. 19-RESID-POST-AA
    11. 103093
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steels
    -0.08
     littérature
    -0.08
     alloys
    -0.08
     inclin
    -0.08
     microsc
    -0.08
     tampa
    -0.07
     Η
    -0.07
     sexta
    -0.07
     symmetry
    -0.07
    ficas
    -0.07
    POSITIVE LOGITS
     substr
    0.18
     tokens
    0.17
     substring
    0.17
     token
    0.15
     segments
    0.15
    _tokens
    0.15
     chunks
    0.15
    Tokens
    0.14
    	token
    0.14
    -token
    0.14
    Activations Density 0.011%

    No Known Activations