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. 119395
    Prev
    Next
    INDEX
    Explanations

    discrimination

    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
    HD
    -0.08
     actifs
    -0.08
     হয়
    -0.08
    umos
    -0.07
     হয়
    -0.07
    MD
    -0.07
    OCI
    -0.07
     kring
    -0.07
    OLED
    -0.07
     ativos
    -0.07
    POSITIVE LOGITS
     catheter
    0.08
     Carol
    0.08
    rna
    0.07
    cdc
    0.07
     phon
    0.07
     microphone
    0.07
    schule
    0.07
    caire
    0.07
     celestial
    0.07
     affaire
    0.07
    Activations Density 0.007%

    No Known Activations