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. 65561
    Prev
    Next
    INDEX
    Explanations

    auth

    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
     locality
    -0.08
     hotel's
    -0.07
     motifs
    -0.07
    ccoli
    -0.07
     Enterprises
    -0.07
    Oo
    -0.07
    -own
    -0.07
    పు
    -0.07
     motive
    -0.07
     Loire
    -0.07
    POSITIVE LOGITS
    ahun
    0.10
     Sunni
    0.09
     operasi
    0.08
     pell
    0.08
     aspirin
    0.08
     hidrat
    0.08
    执行
    0.08
     Zion
    0.08
     outlook
    0.08
     aze
    0.08
    Activations Density 0.001%

    No Known Activations