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. 49609
    Prev
    Next
    INDEX
    Explanations

    ladder

    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
    'g
    -0.10
    гра
    -0.09
    't
    -0.08
    怪
    -0.08
    oct
    -0.08
     plonge
    -0.08
    ден
    -0.08
     job
    -0.07
    "struct
    -0.07
     policing
    -0.07
    POSITIVE LOGITS
     Bug
    0.08
     digitaal
    0.08
     clauses
    0.08
    ugas
    0.08
    風
    0.07
    寫
    0.07
     dign
    0.07
    ulis
    0.07
    aher
    0.07
     Tanner
    0.07
    Activations Density 0.001%

    No Known Activations