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. 29828
    Prev
    Next
    INDEX
    Explanations

    goat

    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
    宗
    -0.08
     beren
    -0.07
     swelling
    -0.07
     Kaff
    -0.07
     fram
    -0.07
     tau
    -0.07
     tame
    -0.07
     CCS
    -0.07
    ッフ
    -0.07
    mest
    -0.07
    POSITIVE LOGITS
    _similarity
    0.08
     आधार
    0.08
     DG
    0.08
     Welfare
    0.08
     Hardy
    0.07
    🏼
    0.07
    _dummy
    0.07
     Difficult
    0.07
    -run
    0.07
     Comm
    0.07
    Activations Density 0.003%

    No Known Activations