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. 90239
    Prev
    Next
    INDEX
    Explanations

    425

    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
    ISTIC
    -0.09
    det
    -0.08
    Popular
    -0.08
    Gain
    -0.08
     mature
    -0.08
    ocyte
    -0.08
    gain
    -0.07
    vict
    -0.07
    济
    -0.07
    Zombie
    -0.07
    POSITIVE LOGITS
    .Context
    0.08
     Cran
    0.08
     England
    0.08
    _rc
    0.08
     rc
    0.08
     სამუშაო
    0.08
     Engelse
    0.08
     tempu
    0.08
     Dress
    0.08
     Clim
    0.08
    Activations Density 0.003%

    No Known Activations