© 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. 23-RESID-POST-AA
    11. 96920
    Prev
    Next
    INDEX
    Explanations

    Web page analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tones
    -0.08
    ohl
    -0.07
     veta
    -0.07
    واف
    -0.07
     mera
    -0.07
     pí
    -0.07
     peças
    -0.07
     quel
    -0.07
     carta
    -0.07
     layers
    -0.07
    POSITIVE LOGITS
     проведение
    0.08
    -holder
    0.08
     Geheim
    0.08
    рани
    0.08
    _pag
    0.08
    Encrypt
    0.08
     encrypted
    0.08
    icillin
    0.08
     Enfer
    0.08
     сут
    0.07
    Activations Density 0.000%

    No Known Activations