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. 112910
    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
    -0.08
     commod
    -0.08
    ొక్క
    -0.08
     poucos
    -0.07
    kill
    -0.07
     tecn
    -0.07
     حال
    -0.07
    [email
    -0.07
    优势
    -0.07
    inat
    -0.07
    POSITIVE LOGITS
    楼
    0.09
    vgl
    0.08
    านคร
    0.08
    ה
    0.08
    answer
    0.08
    alluni
    0.08
     округ
    0.08
     בין
    0.08
    Antwort
    0.08
    Answer
    0.07
    Activations Density 0.018%

    No Known Activations