Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120349
    Prev
    Next
    INDEX
    Explanations

    (

    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
    ,而且
    -0.09
    ussa
    -0.08
     નંબર
    -0.08
    imonio
    -0.08
     wygląda
    -0.08
    係
    -0.07
    idiendo
    -0.07
    你好
    -0.07
     번호
    -0.07
    apes
    -0.07
    POSITIVE LOGITS
     "":↵
    0.09
    ?):
    0.09
     hingegen
    0.08
    :**
    0.08
    ):
    0.08
    ൃത്ത
    0.08
     ):↵
    0.08
    "":
    0.08
     invece
    0.08
     breakthrough
    0.07
    Activations Density 0.066%

    No Known Activations