© 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. 96731
    Prev
    Next
    INDEX
    Explanations

    al

    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
     кисл
    -0.10
    酸
    -0.10
     Citrus
    -0.09
    莓
    -0.09
    .@
    -0.09
     acidic
    -0.09
     citrus
    -0.09
     acid
    -0.08
     oranges
    -0.08
     oauth
    -0.08
    POSITIVE LOGITS
     ally
    0.14
     Ally
    0.11
     organ
    0.10
     al
    0.10
     Organ
    0.09
     schwe
    0.09
     sefyd
    0.09
    anethi
    0.09
     alli
    0.09
     Al
    0.08
    Activations Density 0.004%

    No Known Activations