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. 111860
    Prev
    Next
    INDEX
    Explanations

    period

    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
     sinal
    -0.08
    .sign
    -0.07
    843
    -0.07
    Sch
    -0.07
     seper
    -0.07
    .Float
    -0.07
    -_
    -0.07
    243
    -0.07
    Recognition
    -0.07
    Se
    -0.07
    POSITIVE LOGITS
     तसे
    0.09
     అలాగే
    0.08
     Bow
    0.08
     Daarnaast
    0.08
     apparently
    0.08
     następ
    0.08
    ව
    0.08
     Then
    0.08
     अनि
    0.08
     niti
    0.07
    Activations Density 0.076%

    No Known Activations