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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60985
    Prev
    Next
    INDEX
    Explanations

    code/game development

    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
     iod
    -0.08
     Validators
    -0.08
     deliberately
    -0.08
    ebab
    -0.08
     cryst
    -0.07
     potassium
    -0.07
     antid
    -0.07
    批
    -0.07
     Rutherford
    -0.07
    炒
    -0.07
    POSITIVE LOGITS
     animations
    0.10
    Male
    0.10
    Female
    0.10
    Animation
    0.10
    female
    0.10
    Anim
    0.09
    _pose
    0.09
    male
    0.09
     Animation
    0.09
     mascot
    0.09
    Activations Density 0.010%

    No Known Activations