© 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. 48509
    Prev
    Next
    INDEX
    Explanations

    Code and Portuguese

    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
     распространя
    -0.09
     po
    -0.08
     оценки
    -0.08
     персон
    -0.08
     #"
    -0.08
    изм
    -0.08
    (part
    -0.08
     UFC
    -0.08
     приблиз
    -0.08
     გას
    -0.07
    POSITIVE LOGITS
     knobs
    0.09
     tween
    0.09
     knob
    0.09
    aliases
    0.09
    Variants
    0.08
     KN
    0.08
    Aliases
    0.08
     Tween
    0.08
    KN
    0.07
     Kits
    0.07
    Activations Density 0.000%

    No Known Activations