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. 54118
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     deviennent
    -0.07
     portrait
    -0.07
    Picking
    -0.07
    Dont
    -0.07
     guardians
    -0.07
    edance
    -0.07
    dont
    -0.07
     avocado
    -0.07
     incubation
    -0.07
     devient
    -0.07
    POSITIVE LOGITS
     отдельно
    0.12
     unaffected
    0.11
     separately
    0.10
    裸
    0.10
    未经
    0.10
     afzonder
    0.09
     alone
    0.09
     untouched
    0.09
     daadwerk
    0.09
     nett
    0.09
    Activations Density 0.041%

    No Known Activations