© 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. 96874
    Prev
    Next
    INDEX
    Explanations

    say ASCII or straight

    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
     брен
    -0.09
     extraño
    -0.09
     iwi
    -0.09
     ornament
    -0.09
     parasito
    -0.09
    ienze
    -0.09
     zina
    -0.08
     brincar
    -0.08
     наполн
    -0.08
     estranho
    -0.08
    POSITIVE LOGITS
     ASCII
    0.25
    ASCII
    0.23
     ascii
    0.19
    _ascii
    0.17
    Ascii
    0.15
    .ASC
    0.15
    ascii
    0.15
    _ASC
    0.15
     US
    0.14
     UTF
    0.14
    Activations Density 0.015%

    No Known Activations