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. 58745
    Prev
    Next
    INDEX
    Explanations

    mathematical constraints

    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
     Garten
    -0.09
     Simply
    -0.09
    oyi
    -0.08
     Leistung
    -0.08
     verlieren
    -0.08
     pokaz
    -0.08
     Quel
    -0.08
    sak
    -0.08
    /gin
    -0.08
    /Getty
    -0.08
    POSITIVE LOGITS
    Constraints
    0.12
    _constraints
    0.10
     constrain
    0.10
     constraints
    0.10
    Constraint
    0.10
    .constraints
    0.10
     constrained
    0.10
     constraint
    0.10
     Constraints
    0.09
    constraints
    0.09
    Activations Density 0.069%

    No Known Activations