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. 48852
    Prev
    Next
    INDEX
    Explanations

    conveyed

    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
    elu
    -0.08
    -famous
    -0.07
     hacker
    -0.07
     esports
    -0.07
    িম
    -0.07
     Eventually
    -0.07
    ид
    -0.07
    -average
    -0.07
     kim
    -0.07
    -साथ
    -0.07
    POSITIVE LOGITS
    770
    0.08
     dala
    0.07
     Dimensions
    0.07
    _TERM
    0.07
     thr
    0.07
     tslint
    0.07
     salvage
    0.07
     diversión
    0.07
     carrer
    0.07
     omdat
    0.07
    Activations Density 0.000%

    No Known Activations