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. 15-RESID-POST-AA
    6. 18963
    Prev
    Next
    INDEX
    Explanations

    that

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Correct
    -0.10
     નહીં
    -0.08
    .no
    -0.08
    No
    -0.08
    Keine
    -0.08
    ��
    -0.08
    Cleanup
    -0.07
    .correct
    -0.07
    Returned
    -0.07
     tweak
    -0.07
    POSITIVE LOGITS
     violate
    0.10
     فيه
    0.09
     violates
    0.09
    违反
    0.09
     […]↵↵
    0.09
    ……”↵↵
    0.09
     unlaw
    0.09
    促进
    0.09
     mettant
    0.09
     chứa
    0.08
    Activations Density 0.005%

    No Known Activations