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. 112245
    Prev
    Next
    INDEX
    Explanations

    Abstract

    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
    രിച്ചു
    -0.08
    ್ಸ
    -0.08
    -store
    -0.07
    ిల్ల
    -0.07
     vow
    -0.07
     soak
    -0.07
     kren
    -0.07
    喷
    -0.07
     soaking
    -0.07
     massively
    -0.07
    POSITIVE LOGITS
     counterparts
    0.09
     counterpart
    0.08
    aksi
    0.08
    (ep
    0.08
     competente
    0.08
    ’il
    0.08
    för
    0.08
    rop
    0.08
    ικα
    0.08
     förs
    0.07
    Activations Density 0.021%

    No Known Activations