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. 54093
    Prev
    Next
    INDEX
    Explanations

    Code snippets/instructions

    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
     noise
    -0.08
     elect
    -0.07
     manifold
    -0.07
     ambient
    -0.07
     líder
    -0.07
    候
    -0.07
    ambient
    -0.07
    _W
    -0.07
    ונד
    -0.07
     Č
    -0.07
    POSITIVE LOGITS
     перек
    0.08
    -dro
    0.08
     понадоб
    0.08
    (Rect
    0.08
    gangen
    0.08
     Եվրոպ
    0.08
     ျမန္မာ
    0.08
    anyp
    0.08
    ിക്കാന്
    0.08
    nhof
    0.08
    Activations Density 0.000%

    No Known Activations