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. 27521
    Prev
    Next
    INDEX
    Explanations

    possessive adjectives/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
    sky
    -0.09
    Connectivity
    -0.08
     connectivity
    -0.08
    Reservation
    -0.08
    (db
    -0.08
     vag
    -0.08
    park
    -0.07
    nown
    -0.07
     Connectivity
    -0.07
    ample
    -0.07
    POSITIVE LOGITS
    装修
    0.08
    дән
    0.08
    ച്ച
    0.08
     деңг
    0.08
     adelant
    0.08
    தை
    0.08
    ச்ச
    0.07
    人格
    0.07
     situ
    0.07
    ிருந்த
    0.07
    Activations Density 0.000%

    No Known Activations