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. 113897
    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
     techno
    -0.08
    ्ने
    -0.08
     attr
    -0.08
     أعراض
    -0.08
     atributos
    -0.07
     nuanced
    -0.07
    _attrs
    -0.07
    _perf
    -0.07
    عمل
    -0.07
     tehnolog
    -0.07
    POSITIVE LOGITS
     Qua
    0.08
     Loud
    0.08
     Investor
    0.08
    -grand
    0.07
     Wiel
    0.07
    逆
    0.07
    ..)
    0.07
    0.07
    .NODE
    0.07
    …),
    0.07
    Activations Density 0.006%

    No Known Activations