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. 26984
    Prev
    Next
    INDEX
    Explanations

    Schur's theorem

    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
     grips
    -0.08
    The
    -0.08
    弱
    -0.08
    ای
    -0.08
    estanding
    -0.08
     Athlete
    -0.08
     Schatten
    -0.07
    Dorm
    -0.07
    prek
    -0.07
    Duration
    -0.07
    POSITIVE LOGITS
     IPC
    0.08
    	il
    0.08
     berikut
    0.08
    redi
    0.08
     Послед
    0.08
     explode
    0.08
     satış
    0.08
     urm
    0.08
    	reply
    0.08
     incompat
    0.08
    Activations Density 0.001%

    No Known Activations