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. 87996
    Prev
    Next
    INDEX
    Explanations

    mathematical bounds/distinct values

    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
    yllic
    -0.08
    rc
    -0.07
    ю
    -0.07
     confidential
    -0.07
     tog
    -0.07
     glide
    -0.07
    's
    -0.06
    я
    -0.06
    ful
    -0.06
    conf
    -0.06
    POSITIVE LOGITS
     mindestens
    0.14
    至少
    0.14
     vähemalt
    0.14
     minstens
    0.14
     almeno
    0.13
    .Minimum
    0.13
     obrig
    0.12
     minimum
    0.12
     obrigatório
    0.11
     zwing
    0.11
    Activations Density 0.046%

    No Known Activations