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. 112307
    Prev
    Next
    INDEX
    Explanations

    camera f-ratio

    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
     Ger
    -0.08
     iteration
    -0.08
    ாற்ற
    -0.07
    iet
    -0.07
     Zak
    -0.07
    Ger
    -0.07
     communications
    -0.07
    orgung
    -0.07
     اط
    -0.07
     ger
    -0.07
    POSITIVE LOGITS
     stereo
    0.09
     fein
    0.08
     thumbs
    0.08
    _lim
    0.08
    ရွ
    0.08
    thumb
    0.07
     प्रेस
    0.07
     halal
    0.07
     aspir
    0.07
     Stereo
    0.07
    Activations Density 0.001%

    No Known Activations