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. 12025
    Prev
    Next
    INDEX
    Explanations

    a

    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
    teva
    -0.09
    طرح
    -0.08
     вак
    -0.08
     должна
    -0.08
     posé
    -0.08
     крыш
    -0.08
     бор
    -0.08
     définitivement
    -0.08
     luce
    -0.08
    _PRIV
    -0.08
    POSITIVE LOGITS
    illum
    0.08
    appropriate
    0.08
    errs
    0.07
    weights
    0.07
     unequal
    0.07
    homes
    0.07
    eltjes
    0.07
     constructing
    0.07
    cles
    0.07
    ariot
    0.07
    Activations Density 0.015%

    No Known Activations