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. 90836
    Prev
    Next
    INDEX
    Explanations

    ology

    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
    তার
    -0.07
    Anti
    -0.07
     Anti
    -0.07
    (Control
    -0.07
     Civ
    -0.07
     CORPOR
    -0.07
     Agro
    -0.07
    ipy
    -0.07
    ρισ
    -0.07
    ού
    -0.06
    POSITIVE LOGITS
     thiện
    0.08
     CL
    0.08
     thereby
    0.08
     및
    0.08
    iously
    0.07
     പോലും
    0.07
     thar
    0.07
    �
    0.07
     và
    0.07
    ?...
    0.07
    Activations Density 8.625%

    No Known Activations