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. 3-RESID-POST-AA
    6. 2327
    Prev
    Next
    INDEX
    Explanations

    EXISTS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Naz
    -0.09
     Naz
    -0.08
    Bul
    -0.08
     Monica
    -0.07
     Kirst
    -0.07
     saad
    -0.07
    Ana
    -0.07
    ξε
    -0.07
     sona
    -0.07
     destac
    -0.07
    POSITIVE LOGITS
     molds
    0.09
    �
    0.07
    heits
    0.07
    vf
    0.07
     Spurs
    0.07
     치
    0.07
     horizons
    0.07
    TC
    0.07
    _TE
    0.07
    715
    0.07
    Activations Density 0.003%

    No Known Activations