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. 11661
    Prev
    Next
    INDEX
    Explanations

    by

    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
     finale
    -0.08
    printer
    -0.08
    @"
    -0.08
    洞
    -0.08
    ähler
    -0.07
    と言
    -0.07
    bool
    -0.07
     режиме
    -0.07
    .Tech
    -0.07
     Cha
    -0.07
    POSITIVE LOGITS
     revolving
    0.09
     Kool
    0.08
     torno
    0.08
     দুটি
    0.08
    0.08
     petro
    0.08
    zuführen
    0.08
     consecut
    0.08
    0.07
    人与
    0.07
    Activations Density 0.013%

    No Known Activations