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. 103262
    Prev
    Next
    INDEX
    Explanations

    replacement

    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
    land
    -0.09
     tribal
    -0.08
     frontal
    -0.08
     suprem
    -0.07
     mile
    -0.07
     expense
    -0.07
     सत
    -0.07
     полож
    -0.07
     ankle
    -0.07
     supreme
    -0.07
    POSITIVE LOGITS
    Calculate
    0.08
    BW
    0.08
    SEX
    0.08
     consecut
    0.08
    (Bit
    0.08
     getline
    0.08
    sex
    0.08
    eselect
    0.08
    Amp
    0.07
    ,「
    0.07
    Activations Density 0.001%

    No Known Activations