Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48311
    Prev
    Next
    INDEX
    Explanations

    SQL connection strings

    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
    cija
    -0.08
    OCs
    -0.08
    CW
    -0.08
     嘉
    -0.08
     civ
    -0.07
    ANGE
    -0.07
     Oce
    -0.07
    (line
    -0.07
    umers
    -0.07
    hedral
    -0.07
    POSITIVE LOGITS
     Persist
    0.11
     Integrated
    0.09
     Encrypt
    0.09
     Antrag
    0.09
     Min
    0.09
     Trusted
    0.08
    Persist
    0.08
     Advert
    0.08
     Convert
    0.08
     Nurse
    0.08
    Activations Density 0.000%

    No Known Activations