Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112988
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
     comenz
    -0.07
     nond
    -0.07
     yet
    -0.07
     undis
    -0.07
     сигнал
    -0.07
    gel
    -0.07
     edge
    -0.07
     нест
    -0.07
     dij
    -0.07
    orda
    -0.07
    POSITIVE LOGITS
    legacy
    0.10
     legacy
    0.09
     Hawai
    0.09
     äl
    0.09
     peacefully
    0.09
     dolorem
    0.08
     fazia
    0.08
     yrs
    0.08
     impactful
    0.08
    !*\↵
    0.08
    Activations Density 0.048%

    No Known Activations