© 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. 23-RESID-POST-AA
    11. 97876
    Prev
    Next
    INDEX
    Explanations

    B

    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
    ail
    -0.09
     bero
    -0.08
     frantic
    -0.08
     sustitu
    -0.08
     cyclic
    -0.07
    &rsquo
    -0.07
    among
    -0.07
     Inject
    -0.07
    Charges
    -0.07
     Prod
    -0.07
    POSITIVE LOGITS
    ॉल
    0.10
    adm
    0.10
    ంత
    0.10
    ால்
    0.10
    älle
    0.10
     tournament
    0.09
    ॉलर
    0.09
    uteurs
    0.09
    Tournament
    0.09
    ాల్
    0.08
    Activations Density 0.011%

    No Known Activations