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. 58369
    Prev
    Next
    INDEX
    Explanations

    "--"

    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
    -fashioned
    -0.08
    વણી
    -0.08
    -Adresse
    -0.07
    વાનું
    -0.07
    [I
    -0.07
     Puppet
    -0.07
    用品
    -0.07
    ermont
    -0.07
    anato
    -0.06
     Kommun
    -0.06
    POSITIVE LOGITS
    0.08
    0.08
     Må
    0.07
     óleo
    0.07
     salga
    0.07
     lancer
    0.07
    icer
    0.07
     prism
    0.07
    高清
    0.07
    HEADER
    0.07
    Activations Density 0.003%

    No Known Activations