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. 29968
    Prev
    Next
    INDEX
    Explanations

    philosophy of mind

    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
    _evt
    -0.09
     sad
    -0.08
     motif
    -0.07
     magician
    -0.07
    ircle
    -0.07
    _typ
    -0.07
     büy
    -0.07
    da
    -0.07
     reminded
    -0.07
     clo
    -0.07
    POSITIVE LOGITS
    నీ
    0.08
    parency
    0.08
     сустав
    0.08
     Konsequ
    0.08
     Therap
    0.08
     зуб
    0.08
    वाही
    0.08
    _NONE
    0.07
     Sole
    0.07
     Zeiten
    0.07
    Activations Density 0.002%

    No Known Activations