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. 43631
    Prev
    Next
    INDEX
    Explanations

    refer

    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
    ((((
    -0.07
     pnl
    -0.07
     Timber
    -0.07
     coarse
    -0.07
    144
    -0.07
    sf
    -0.07
    smith
    -0.07
    131
    -0.07
     sourced
    -0.07
    fiber
    -0.07
    POSITIVE LOGITS
    encing
    0.09
    々
    0.09
    lichkeiten
    0.09
     إليها
    0.09
     Dora
    0.08
     Tarragona
    0.08
    稱
    0.08
    称
    0.08
    -vous
    0.08
    於
    0.07
    Activations Density 0.018%

    No Known Activations