© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31137
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     impossible
    -0.09
     이미
    -0.09
     ……
    -0.08
     കര്
    -0.08
     невозможно
    -0.08
    -chair
    -0.07
    წუხ
    -0.07
    -members
    -0.07
     trusts
    -0.07
     atmosphere
    -0.07
    POSITIVE LOGITS
     Peaks
    0.09
    मीटर
    0.09
     peaks
    0.08
     wave
    0.08
    Spacing
    0.08
    ชัย
    0.08
     waveform
    0.08
     spacing
    0.08
    σει
    0.08
    slos
    0.08
    Activations Density 0.018%

    No Known Activations