Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78673
    Prev
    Next
    INDEX
    Explanations

    grading/evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milliarden
    -0.09
    angement
    -0.08
     Prize
    -0.08
     feats
    -0.08
     enormously
    -0.08
     Vorteile
    -0.08
    ~↵↵
    -0.07
    ledning
    -0.07
    tragen
    -0.07
    ctic
    -0.07
    POSITIVE LOGITS
     ухуд
    0.10
     midway
    0.10
     cautiously
    0.10
     mediocre
    0.09
     dow
    0.09
     cautious
    0.09
     conscience
    0.08
     downg
    0.08
     ratings
    0.08
    (wait
    0.08
    Activations Density 0.013%

    No Known Activations