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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 935
    Prev
    Next
    INDEX
    Explanations

    языке

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avir
    -0.08
     között
    -0.07
    産
    -0.07
    ‌బ
    -0.07
    Healing
    -0.07
     romantic
    -0.07
    cribed
    -0.07
     Editorial
    -0.07
     therapist
    -0.07
    difficulty
    -0.07
    POSITIVE LOGITS
     Junge
    0.08
     HL
    0.08
    .dsl
    0.08
     hl
    0.08
     Zack
    0.08
    cco
    0.08
     LLVM
    0.08
    hl
    0.08
     देखकर
    0.08
     AVR
    0.07
    Activations Density 0.008%

    No Known Activations