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. 113986
    Prev
    Next
    INDEX
    Explanations

    wrestling

    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
    描
    -0.09
    <Location
    -0.08
    .Location
    -0.08
    .location
    -0.07
    	location
    -0.07
     heli
    -0.07
    location
    -0.07
    虹
    -0.07
    摄影
    -0.07
    $\
    -0.07
    POSITIVE LOGITS
     wrestling
    0.14
     Wrestling
    0.12
     wrest
    0.12
     opponent
    0.12
     wrestler
    0.10
     opponents
    0.10
     арм
    0.10
     соревн
    0.09
     CSA
    0.09
    Opponent
    0.09
    Activations Density 0.015%

    No Known Activations