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. 11-RESID-POST-AA
    6. 106006
    Prev
    Next
    INDEX
    Explanations

    space missions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parsley
    -0.09
     BCrypt
    -0.09
     hashed
    -0.08
     erotic
    -0.08
     BDSM
    -0.08
     martial
    -0.08
     sindical
    -0.08
     cramps
    -0.08
     professions
    -0.08
     indulg
    -0.08
    POSITIVE LOGITS
     missions
    0.15
     spacecraft
    0.15
     Missions
    0.13
     launched
    0.12
     mission
    0.12
     NASA
    0.12
     मिश
    0.12
     Pioneer
    0.11
     rover
    0.11
     Voyager
    0.11
    Activations Density 0.025%

    No Known Activations