© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102787
    Prev
    Next
    INDEX
    Explanations

    error messages

    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
     From
    -0.10
    from
    -0.09
    From
    -0.09
     from
    -0.09
    .from
    -0.09
    _from
    -0.08
     Initially
    -0.08
    matching
    -0.08
    Initially
    -0.08
    -match
    -0.08
    POSITIVE LOGITS
    	perror
    0.16
     perror
    0.15
    	throw
    0.12
    .Fatalf
    0.12
    	panic
    0.11
    .Fatal
    0.11
     strerror
    0.11
    _FATAL
    0.11
    _ERROR
    0.10
     abort
    0.10
    Activations Density 0.006%

    No Known Activations