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. 90815
    Prev
    Next
    INDEX
    Explanations

    cruises

    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
     angular
    -0.08
     potency
    -0.08
     hect
    -0.08
     Angular
    -0.07
     contund
    -0.07
     scour
    -0.07
     soms
    -0.07
    Angular
    -0.07
     кыр
    -0.07
     uns
    -0.07
    POSITIVE LOGITS
    酒店
    0.12
     होटल
    0.12
     호텔
    0.11
     hotel
    0.11
    Hotel
    0.11
     Hotel
    0.11
    ホテル
    0.10
    hotel
    0.10
     HOTEL
    0.10
     hotel's
    0.09
    Activations Density 0.025%

    No Known Activations