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. 111925
    Prev
    Next
    INDEX
    Explanations

    ensitive

    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
     todd
    -0.09
    牲
    -0.09
     Bons
    -0.08
     съд
    -0.08
    未
    -0.08
     unmet
    -0.08
     vec
    -0.08
    .mine
    -0.08
    mine
    -0.08
     未
    -0.08
    POSITIVE LOGITS
     Hash
    0.08
    poke
    0.08
    Hash
    0.07
     manner
    0.07
    'al
    0.07
     transcription
    0.07
     treats
    0.07
    except
    0.07
     wyją
    0.07
     transcript
    0.07
    Activations Density 0.005%

    No Known Activations