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. 43102
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    нәр
    -0.09
    -The
    -0.09
    ison
    -0.08
    Tutorial
    -0.08
    Fil
    -0.08
    Theo
    -0.08
     ordre
    -0.08
    گ
    -0.08
    Parameters
    -0.08
    Liked
    -0.07
    POSITIVE LOGITS
     Vertr
    0.09
     postul
    0.08
     hitters
    0.08
     sva
    0.08
     w
    0.08
     paradox
    0.07
     distrust
    0.07
     ditt
    0.07
     forbidden
    0.07
     Kok
    0.07
    Activations Density 0.014%

    No Known Activations