© 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. 97346
    Prev
    Next
    INDEX
    Explanations

    end

    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
    र्ध
    -0.09
    baix
    -0.09
     Dienstag
    -0.08
     recoge
    -0.08
    ാതെ
    -0.08
     пой
    -0.08
     трас
    -0.08
    .zeros
    -0.08
     palais
    -0.08
    െയാണ്
    -0.08
    POSITIVE LOGITS
     planet
    0.09
     özg
    0.07
     |\
    0.07
     Earth
    0.07
     |
    0.07
    |↵↵
    0.07
    Empire
    0.07
    097
    0.07
    Ear
    0.07
     xy
    0.07
    Activations Density 0.001%

    No Known Activations