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. 67855
    Prev
    Next
    INDEX
    Explanations

    absorbing

    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
     extr
    -0.08
     সাহ
    -0.08
    xm
    -0.07
    샵
    -0.07
    hrad
    -0.07
     sudo
    -0.07
     crews
    -0.07
    شی
    -0.07
    Nee
    -0.07
    Champion
    -0.07
    POSITIVE LOGITS
     reachable
    0.08
    -terminal
    0.08
     reached
    0.08
     raggi
    0.08
     terminal
    0.08
     sticky
    0.07
    વાના
    0.07
     Tears
    0.07
    Terminal
    0.07
    _terminal
    0.07
    Activations Density 0.003%

    No Known Activations