© 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. 29779
    Prev
    Next
    INDEX
    Explanations

    Cayley graph

    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
    ended
    -0.08
     صدر
    -0.08
     nõ
    -0.08
    tees
    -0.08
     Ανα
    -0.08
    әттә
    -0.08
     বৰ
    -0.08
     రిలీజ్
    -0.08
     تعلق
    -0.07
     విడుదల
    -0.07
    POSITIVE LOGITS
    _mut
    0.08
     Lighting
    0.08
    .Stop
    0.08
     libert
    0.08
     liberté
    0.07
     Mut
    0.07
     Hern
    0.07
    _OFF
    0.07
     Goth
    0.07
     Osc
    0.07
    Activations Density 0.000%

    No Known Activations