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. 53647
    Prev
    Next
    INDEX
    Explanations

    as

    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
    🏼
    -0.08
     meanwhile
    -0.08
     lighting
    -0.07
     Mic
    -0.07
    _GUI
    -0.07
    getting
    -0.07
     എത്ത
    -0.07
    435
    -0.07
    quando
    -0.07
    _med
    -0.07
    POSITIVE LOGITS
     Bw
    0.09
     얼마
    0.09
     Jij
    0.09
     sot
    0.08
     lan
    0.08
     либо
    0.08
    "P
    0.08
     quadru
    0.08
     szt
    0.08
    "strconv
    0.08
    Activations Density 0.020%

    No Known Activations