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. 46941
    Prev
    Next
    INDEX
    Explanations

    caramel

    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
     forall
    -0.08
     Freel
    -0.08
     versa
    -0.08
     gemeente
    -0.07
     determinant
    -0.07
    asile
    -0.07
    Transmit
    -0.07
    Institute
    -0.07
     organism
    -0.07
    utek
    -0.07
    POSITIVE LOGITS
     dessert
    0.09
     Blonde
    0.08
     Mist
    0.08
     Venez
    0.08
     coul
    0.08
     Pit
    0.08
     vodka
    0.08
     chees
    0.07
    Pit
    0.07
    טע
    0.07
    Activations Density 0.003%

    No Known Activations