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. 78651
    Prev
    Next
    INDEX
    Explanations

    Dioxide and related compounds

    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
    厚
    -0.10
     laughter
    -0.09
     familiares
    -0.09
     игроков
    -0.09
     tearing
    -0.08
     machten
    -0.08
     laborales
    -0.08
    ષ્ણ
    -0.08
     Gav
    -0.08
     أث
    -0.08
    POSITIVE LOGITS
    -filter
    0.08
     formazione
    0.08
     illumination
    0.08
     dojo
    0.07
     jpg
    0.07
     elucid
    0.07
     cip
    0.07
     discern
    0.07
    cnt
    0.07
     listado
    0.07
    Activations Density 0.003%

    No Known Activations