© 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. 5824
    Prev
    Next
    INDEX
    Explanations

    per

    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
     zai
    -0.09
     için
    -0.08
    ayed
    -0.08
     artık
    -0.08
    Ai
    -0.08
    ati
    -0.08
     ay
    -0.08
     στις
    -0.08
    -eche
    -0.08
    ni
    -0.08
    POSITIVE LOGITS
    дати
    0.09
    дап
    0.09
     comments
    0.09
    нести
    0.09
    ചര
    0.08
    इत
    0.08
    б
    0.08
     शुभ
    0.08
    وغ
    0.08
    ल्प
    0.08
    Activations Density 0.004%

    No Known Activations