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. 90633
    Prev
    Next
    INDEX
    Explanations

    Selling homes

    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
    fan
    -0.08
    方便
    -0.08
     accumulating
    -0.07
    _WRAP
    -0.07
     waistband
    -0.07
    AW
    -0.07
    束
    -0.07
     conveniently
    -0.07
    DI
    -0.07
    _SH
    -0.07
    POSITIVE LOGITS
     professionalism
    0.13
     REALTORS
    0.11
     charisma
    0.11
     demeanor
    0.10
     Eindruck
    0.10
     uitstraling
    0.10
     aantrekk
    0.10
     CEOs
    0.10
     Realtors
    0.10
     attractiveness
    0.09
    Activations Density 0.045%

    No Known Activations