© 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. 48078
    Prev
    Next
    INDEX
    Explanations

    Gifts and experiences

    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
     offerings
    -0.10
     friendliness
    -0.09
     ponud
    -0.09
     rewarding
    -0.08
     angebot
    -0.08
     rewards
    -0.08
     generosity
    -0.08
     nabíz
    -0.08
     sprzeda
    -0.08
     lää
    -0.08
    POSITIVE LOGITS
     engraved
    0.13
     tickets
    0.13
    Tickets
    0.12
     experiencias
    0.11
    utschein
    0.11
     Tickets
    0.11
     experiences
    0.11
     Experiences
    0.11
     spa
    0.11
     limo
    0.11
    Activations Density 0.034%

    No Known Activations