Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111877
    Prev
    Next
    INDEX
    Explanations

    trace

    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
    strand
    -0.08
     odl
    -0.08
    ISTRATION
    -0.07
    mented
    -0.07
     sch
    -0.07
    acency
    -0.07
    /general
    -0.07
     kër
    -0.07
     RN
    -0.07
     euch
    -0.07
    POSITIVE LOGITS
    -cut
    0.08
    .Trace
    0.08
    Autos
    0.07
    backs
    0.07
     Judith
    0.07
    hten
    0.07
     pup
    0.07
    trace
    0.07
    ht
    0.07
     harbor
    0.07
    Activations Density 0.007%

    No Known Activations