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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76529
    Prev
    Next
    INDEX
    Explanations

    shape intersections

    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
    ligen
    -0.08
    Upgrade
    -0.08
    σουμε
    -0.08
     derail
    -0.08
     flexibil
    -0.08
    tobuf
    -0.08
    _upgrade
    -0.07
     nonlinear
    -0.07
    升级
    -0.07
     cometer
    -0.07
    POSITIVE LOGITS
     Desc
    0.09
     traversal
    0.09
     togg
    0.09
     Travers
    0.08
    (ROOT
    0.08
    (cam
    0.08
     immersive
    0.08
     restores
    0.08
    Desc
    0.08
    (draw
    0.08
    Activations Density 0.005%

    No Known Activations