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. 42331
    Prev
    Next
    INDEX
    Explanations

    治疗

    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
     Herd
    -0.09
    Tau
    -0.08
    ================
    -0.08
     seemed
    -0.08
    enses
    -0.08
     모습을
    -0.07
    OCKET
    -0.07
    Pig
    -0.07
    황
    -0.07
     creek
    -0.07
    POSITIVE LOGITS
     lyrics
    0.09
     manga
    0.08
     kas
    0.08
     genre
    0.07
    -oriented
    0.07
     ::
    0.07
     subdivision
    0.07
    ятся
    0.07
     anot
    0.07
     (::
    0.07
    Activations Density 0.008%

    No Known Activations