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. 77917
    Prev
    Next
    INDEX
    Explanations

    elaboration and detail

    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
     фикс
    -0.08
     civ
    -0.08
     cij
    -0.08
    سات
    -0.08
    Populate
    -0.08
    قتل
    -0.08
     arre
    -0.08
     pang
    -0.08
    ועה
    -0.08
    ресс
    -0.07
    POSITIVE LOGITS
    0.08
    redis
    0.08
    呢
    0.08
    blic
    0.08
    orig
    0.07
    旅
    0.07
     converter
    0.07
    。当
    0.07
    contained
    0.07
    ero
    0.07
    Activations Density 0.018%

    No Known Activations