© 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. 6229
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     Fast
    -0.08
     ఏ
    -0.07
    ΑΙ
    -0.07
     raha
    -0.07
     سریع
    -0.07
     |=
    -0.07
     ^=
    -0.07
    UES
    -0.07
    egi
    -0.07
    ues
    -0.07
    POSITIVE LOGITS
     Unite
    0.08
    стри
    0.08
    ဒ
    0.08
    ltre
    0.08
     unite
    0.08
    _gray
    0.08
    står
    0.08
    пания
    0.08
    stor
    0.08
     adhesion
    0.08
    Activations Density 0.000%

    No Known Activations