© 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. 23-RESID-POST-AA
    11. 97424
    Prev
    Next
    INDEX
    Explanations

    tortillas/wraps

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chunk
    -0.09
     Schmuck
    -0.08
     subtree
    -0.08
    mtree
    -0.08
     ballast
    -0.08
     Boulder
    -0.08
     Quincy
    -0.08
     syndic
    -0.08
     Boss
    -0.08
    Boss
    -0.08
    POSITIVE LOGITS
     tortillas
    0.25
     tortilla
    0.22
     wraps
    0.17
     wrappers
    0.16
    .WRAP
    0.16
    Wrap
    0.15
     Wrap
    0.15
     wrap
    0.15
     wrapper
    0.15
    _wrap
    0.15
    Activations Density 0.028%

    No Known Activations