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. 112746
    Prev
    Next
    INDEX
    Explanations

    Naming

    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
    ák
    -0.08
    êmica
    -0.08
    ægt
    -0.07
    eload
    -0.07
     یه
    -0.07
     apresentar
    -0.07
     IUser
    -0.07
    .ep
    -0.07
    emap
    -0.07
    ేదు
    -0.07
    POSITIVE LOGITS
     aptly
    0.11
     nomen
    0.11
     referring
    0.09
     perché
    0.08
     refers
    0.08
     verlie
    0.08
    natur
    0.08
     потому
    0.08
    Convention
    0.08
     loosely
    0.08
    Activations Density 0.051%

    No Known Activations