© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 572
    Prev
    Next
    INDEX
    Explanations

    visualization

    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
     tolerate
    -0.08
    Ros
    -0.08
     convention
    -0.08
    _dis
    -0.07
    OPEN
    -0.07
    _SU
    -0.07
    thi
    -0.07
     opent
    -0.07
     opbreng
    -0.07
    emp
    -0.07
    POSITIVE LOGITS
    Hiring
    0.10
     Hiring
    0.09
     vividly
    0.09
    իչ
    0.09
     وتح
    0.09
     فراہم
    0.09
    ીક
    0.08
     vivid
    0.08
     ذهن
    0.08
     puesto
    0.08
    Activations Density 0.010%

    No Known Activations