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. 52998
    Prev
    Next
    INDEX
    Explanations

    integers and numbers

    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
    igure
    -0.09
     viewer
    -0.08
    Viewer
    -0.08
    Ako
    -0.07
     ambassadors
    -0.07
     kidney
    -0.07
    นี้
    -0.07
     FEMA
    -0.07
    Touched
    -0.07
    renal
    -0.07
    POSITIVE LOGITS
     hacerse
    0.09
    丁
    0.08
    ٍ
    0.08
     --->
    0.08
     expressly
    0.07
     utf
    0.07
    ခြ
    0.07
     whim
    0.07
    ാണ്
    0.07
    -api
    0.07
    Activations Density 0.044%

    No Known Activations