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. 54229
    Prev
    Next
    INDEX
    Explanations

    code and regex

    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
     матери
    -0.07
     ranging
    -0.07
    最快
    -0.07
     fairly
    -0.07
     pretty
    -0.07
     moderate
    -0.07
     llegar
    -0.07
     आहेत
    -0.06
     first
    -0.06
     posts
    -0.06
    POSITIVE LOGITS
     попыт
    0.15
     Attempt
    0.14
     inappropriate
    0.14
    .invalid
    0.14
     INVALID
    0.14
     Invalid
    0.14
    invalid
    0.14
    Attempt
    0.13
    INVALID
    0.13
     invalid
    0.13
    Activations Density 0.021%

    No Known Activations