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. 67552
    Prev
    Next
    INDEX
    Explanations

    Moving buildings

    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
    amut
    -0.09
    .opend
    -0.07
    网
    -0.07
    誘惑
    -0.07
     penetrate
    -0.07
     creators
    -0.07
    avored
    -0.07
     penetr
    -0.07
    Crow
    -0.07
    acro
    -0.07
    POSITIVE LOGITS
     traslad
    0.12
     relocated
    0.10
     traslado
    0.10
    搬
    0.10
     relocating
    0.10
     relocation
    0.10
     transpl
    0.10
     reloc
    0.10
     transporting
    0.09
     transported
    0.09
    Activations Density 0.025%

    No Known Activations