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. 76008
    Prev
    Next
    INDEX
    Explanations

    scientific predictions and hypotheses

    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
    ousal
    -0.09
    376
    -0.09
    рани
    -0.09
     presso
    -0.08
    ppelin
    -0.08
    Assemblée
    -0.08
    টে
    -0.08
     WPA
    -0.08
    ਾਸ
    -0.08
     Transcript
    -0.08
    POSITIVE LOGITS
     predictions
    0.14
     hypotheses
    0.14
     Predictions
    0.12
     predicts
    0.12
     अपे
    0.12
    _predictions
    0.12
     voorsp
    0.11
     predicting
    0.11
    pred
    0.11
     predicted
    0.11
    Activations Density 0.010%

    No Known Activations